Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to political entities such as countries, organizations, and governments

    oai_token-act-pair · gpt-3.5-turbo

    references to institutions, organizations, and entities related to governance and society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urations
    -0.90
    olas
    -0.81
    irens
    -0.75
    elight
    -0.75
    amas
    -0.73
    poons
    -0.68
    redients
    -0.67
    atures
    -0.66
     Machines
    -0.66
    oha
    -0.65
    POSITIVE LOGITS
     member
    1.14
     legislator
    1.02
     competitor
    1.02
     employee
    0.98
    builder
    0.95
     sponsor
    0.95
    member
    0.94
     entity
    0.93
     leader
    0.91
     administrator
    0.90
    Act Density 0.204%

    No Known Activations